Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to government intelligence activities and policies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to foreign intelligence and policy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TPS
    -0.78
    Cooldown
    -0.75
    amaz
    -0.74
    FORMATION
    -0.73
    raper
    -0.70
    CHAT
    -0.68
    esville
    -0.67
    Roll
    -0.66
    GM
    -0.66
    ikan
    -0.64
    POSITIVE LOGITS
     Confederation
    0.75
     correspondent
    0.73
     Affairs
    0.73
     espionage
    0.72
    bia
    0.69
     subt
    0.69
     Diplom
    0.68
     abroad
    0.68
    uador
    0.68
     Lavrov
    0.67
    Act Density 0.051%

    No Known Activations